Bug triage processes are intended to assign bug reports to appropriate developers effectively, but they typically become bottlenecks in the development process—especially for large-scale software projects. Recently, several machine learning approaches, including deep learning-based approaches, have been proposed to recommend an appropriate developer automatically by learning past assignment patterns. In this paper, we propose a deep learning-based bug triage technique using a convolutional neural network (CNN) with three different word representation techniques: Word to Vector (Word2Vec ), Global Vector (GloVe), and Embeddings from Language Models (ELMo). Experiments were performed on datasets from well-known large-scale open-source projects, such as Eclipse and Mozilla, and top-k accuracy was measured as an evaluation metric. The experimental results suggest that the ELMo-based CNN approach performs best for the bug triage problem. GloVe-based CNN slightly outperforms Word2Vec-based CNN in many cases. Word2Vec-based CNN outperforms GloVe-based CNN when the number of samples per class in the dataset is high enough.

Many bugs and defects occur during software testing and maintenance. These bugs should be resolved as soon as possible, to improve software quality. However, bug triage aims to solve these bugs by assigning the reported bugs to an appropriate developer or list of developers. It is an arduous task for a human triager to assign an appropriate developer to a bug report, when there are several developers with different skills, and several automated and semi-automated triage systems have been proposed in the last decade. Some recent techniques have suggested possibilities for the development of an effective triage system. However, these techniques require improvement. In previous work, we proposed a heterogeneous graph representation for bug triage, using word–word edges and word-bug document co-occurrences to build a heterogeneous graph of bug data. Cosine similarity is used to weight the word–word edges. Then, a graph convolution network is used to learn a heterogeneous graph representation. This paper extends our previous work by adopting different similarity metrics and correlation metrics for weighting word–word edges. The method was validated using different small and large datasets obtained from large-scale open-source projects. The top-k accuracy metric was used to evaluate the performance of the bug triage system. The experimental results showed that the point-wise mutual information of the proposed model was better than that of other word–word weighting methods, and our method had better accuracy for large datasets than other recent state-of-the-art methods. The proposed method with point-wise mutual information showed 3% to 6% higher top-1 accuracy than state-of-the-art methods for large datasets.

Recently, deep reinforcement learning (RL) technologies have been considered as a feasible solution for tackling combinatorial problems in various research and engineering areas. Motivated by this recent success of RL-based approaches, in this paper, we focus on how to utilize RL technologies in the context of real-time system research. Specifically, we first formulate the problem of fixed-priority assignments for multi-processor real-time scheduling, which has long been considered challenging in the real-time system community, as a combinatorial problem. We then propose the RL-based priority assignment model Panda that employs (i) a taskset embedding mechanism driven by attention-based encoder-decoder deep neural networks, hence enabling to efficiently extract useful features from the dynamic relation of periodic tasks. We also present two optimization schemes tailored to adopt RL for real-time task scheduling problems: (ii) the response time analysis (RTA)-based policy gradient RL and guided learning schemes, which facilitate the training processes of the Panda model. To the best of our knowledge, our approach is the first to employ RL for real-time task scheduling. Through various experiments, we show that Panda is competitive with well-known heuristic algorithms for real-time task scheduling upon a multi-processor platform, and it often outperforms them in large-scale non-trivial settings, e.g., achieving an average 7.7% enhancement in schedulability ratio for a testing system configuration of 64-sized tasksets and an 8-processor platform.

Parallelization of tasks and efficient utilization of processors are considered important and challenging in operating large-scale real-time systems. Recently, deep reinforcement learning (DRL) was found to provide effective solutions to various combinatorial optimization problems. In this paper, inspired by recent achievements in DRL, we employ DRL techniques for scheduling a directed acyclic graph (DAG) task in which a set of non-preemptive subtasks are specified by precedence conditions among them. We propose a DRL-based priority assignment model for scheduling a DAG task on a multiprocessor system, named GoSu , which adapts a graph convolution network (GCN) to process a complex interdependent task structure and minimize the makespan of a DAG task. Our proposed model makes use of both temporal and structural features in a DAG to effectively learn a priority-based scheduling policy via GCN and policy gradient methods. With comprehensive evaluations, we verify that our model shows comparable performance to several state-of-the-art DAG task scheduling algorithms, and outperforms them by 2~3% in the slowdown of achieved makespans particularly in nontrivial system configurations where workloads are neither too small nor heavy compared to the given number of processors. We also analyze the priority assignment behaviors of our model by leveraging a regression method that imitates the learned policy of the model.

Predicting the fix time of a bug is important for managing the resources and release milestones of a software development project. However, it is considered non-trivial to achieve high accuracy when predicting bug-fix times. We view that such difficulties come from the lack of continuous or posterior estimation based on subsequent developers’ activities after a bug is initially reported. In this paper, we formulate the problem of bug-fix time prediction into a continual update of estimates with more activities. Logging data of bug-related activities that are streamed to a bug tracking system change the bug reports, enabling us to recalculate predictions over time. To do so, we propose a deep learning-based two-staged activity stream embedding model, DASENet that employs (i) a merged network for extracting contextual features across different types of logs, and (ii) a sequence network for exploring temporal relations of the logs. Through experiments with bug tracking system datasets from open source projects including Firefox, Chromium, and Eclipse, we show that DASENet achieves stable performance, e.g., for the Firefox dataset, top-1 accuracy of 4.6 to 8.5 % higher than other state-of-the-art works. Our approach also provides a transferable structure, yielding robust performance with a small dataset for different tasks; the DASENet model trained with a small dataset of about 900 samples (2 % of a full dataset) can show competitive performance to the other models with a full dataset. To the best of our knowledge, we are the first to employ deep learning on log streams in the context of bug-fix time prediction.